INDEX

Explanations

phrases indicating the presence or actions of people and their relationships with specific events or objects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fowler

-0.15

azz

-0.15

quisite

-0.14

è¡

-0.14

oll

-0.14

 Brief

-0.13

 Frag

-0.13

yl

-0.13

anzi

-0.13

Å¡ti

-0.13

POSITIVE LOGITS

Ð¾Ð»Ñİ

0.16

ascus

0.16

_TA

0.14

å¿ł

0.14

fabs

0.14

 commissions

0.14

riv

0.13

ADOW

0.13

ÄĻp

0.13

ERSHEY

0.13

Activations Density 0.069%

phrases indicating the presence or actions of people and their relationships with specific events or objects

No Comments

No Known Activations